Designing AI-mediated interactive learning environments for communication skills: Insights from two implementations
Developing communication skills remains a core challenge in higher education, particularly in providing scalable opportunities for practice and feedback. This study explores how artificial intelligence (AI)-mediated systems function as interactive learning environments for communication skills development. Two implementations are examined: a voice-only conversational AI-mediated system used across health disciplines and a digital human avatar used in a business unit. A mixed-methods design was employed, combining quantitative survey data and qualitative content. Findings highlighted three key affordances: repeated low-stakes practice, immediate feedback, and flexible engagement. Students reported increased confidence and perceived skill development. Limitations included conversational inaccuracies, realism, technical reliability, and feedback consistency. Importantly, findings indicate that the effectiveness of AI systems is strongly influenced by prompt design, scenario construction, and alignment with learner level. This paper reframes AI tools not as autonomous technologies, but as designed interactive learning environments requiring careful pedagogical integration. Implications are discussed for the design of AI-supported learning activities, particularly in contexts involving oral communication and authentic assessment.
Authors
- Ashleigh Angus
- Naomi Cocks (ORCID: https://orcid.org/0000-0002-1744-6979)
- Phoebe Simpson (ORCID: https://orcid.org/0000-0003-4025-9108)
- Ife MacKenzie
- Matt Reed
- Brenton Lush (ORCID: https://orcid.org/0009-0005-6820-8398)
- Marcelo Jopia Vilches
- Christina FERNANDES
- Emily Calton
- Mitch Low
- Sonia Raghav
- Michael Borck
- Janet Beilby
Institutions
- Curtin University (AU)
Publication Details
- Journal
- ASCILITE Publications
- Published
- 2026-11-17
- DOI
- https://doi.org/10.65106/apubs.2026.3184
- Primary Topic
- Artificial Intelligence in Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00